27 matches found
Veritensor
🛡️ Veritensor: AI Data & Artifact Security Veritensor is the Anti-Virus for AI Artifacts and the ultimate Firewall for RAG pipelines. It secures the entire AI Supply Chain by scanning the artifacts that traditional SAST tools miss: Models, Datasets, RAG Documents, and Notebooks. Veritensor shift...
OWASP-Top-10-Neocloud-and-AI-Data-Center-Security-Risks
Top 10 Neocloud and AI Data Center Security Risks Harden the metal beneath the model. 🌐 Project page: owasp.org/projects/top-10-neocloud-and-ai-data-center-security-risks Executive Summary AI workloads depend on complex infrastructure spanning accelerators, high-speed networks, storage,...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +924 more potentially affected by CVE-2026-78683 via nltk (>=3.0.0, <=3.9.4)
nltk PYPI version =3.0.0, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-78683 Source advisory: OSV:GHSA-RHP5-R9X4-F5G2...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +929 more potentially affected by CVE-2026-81725 via nltk (>=3.0.0, <=3.10.2)
nltk PYPI version =3.0.0, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-81725 Source advisory: SNYK:PYTHON-NLTK-19513454...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +929 more potentially affected by CVE-2026-79676 via nltk (>=3.0.0, <=3.10.2)
nltk PYPI version =3.0.0, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-79676 Source advisory: SNYK:PYTHON-NLTK-19276672...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +931 more potentially affected by CVE-2026-79674 via nltk (>=2.0.4, <=3.10.2)
nltk PYPI version =2.0.4, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-79674 Source advisory: MEND:CVE-2026-79674...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +926 more potentially affected by CVE-2026-12261 via nltk (>=2.0.4, <=3.9.4)
nltk PYPI version =2.0.4, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-12261 Source advisory: MEND:CVE-2026-12261...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +924 more potentially affected by CVE-2026-12075 via nltk (>=3.0.0, <=3.9.4)
nltk PYPI version =3.0.0, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-12075 Source advisory: GHSA-QVV7-CG9C-W4X3...
aa-rag (>=0.4.2, <=0.4.3), aaa-ml-datasets-course (1.0.0) +924 more potentially affected by CVE-2026-12061 via nltk (>=3.0.0, <=3.9.4)
nltk PYPI version =3.0.0, =0.4.2, =0.2.3, =0.0.1, =0.2.0, =0.0.4, =0.4.0, =0.0.1, =0.1.0, =1.1.0, =0.1.0, =1.0.0 and more Source cves: CVE-2026-12061 Source advisory: GHSA-FG7F-2386-8897...
New Microsoft Purview innovations for Fabric to safely accelerate your AI transformation
As organizations adopt AI, security and governance remain core primitives for safe AI transformation and acceleration. After all, data leaders are aware of the notion that: Your AI is only as good as your data. Organizations are skeptical about AI transformation due to concerns of sensitive data...
How To Build Ransomware-Resilient AI Data Pipelines: A Practical Guide for Modern Enterprises
Modern enterprises depend on AI data pipelines for analytics and automated decision-making. As these pipelines become more integrated…...
Deserialization of Untrusted Data
Overview ai-data-science-team is a Build and run an AI-powered data science team. Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the loadpickle function in aidatascienceteam/tools/dataloader.py. An attacker can execute arbitrary code by supplying a...
Securing Data in the AI Era
The 2025 Data Risk Report: Enterprises face potentially serious data loss risks from AI-fueled tools. Adopting a unified, AI-driven approach to data security can help. As businesses increasingly rely on cloud-driven platforms and AI-powered tools to accelerate digital transformation, the stakes f...
Your AI Agents Might Be Leaking Data — Watch this Webinar to Learn How to Stop It
Generative AI is changing how businesses work, learn, and innovate. But beneath the surface, something dangerous is happening. AI agents and custom GenAI workflows are creating new, hidden ways for sensitive enterprise data to leak —and most teams don't even realize it. If you're building,...
⚡ Weekly Recap: iPhone Spyware, Microsoft 0-Day, TokenBreak Hack, AI Data Leaks and More
Some of the biggest security problems start quietly. No alerts. No warnings. Just small actions that seem normal but aren't. Attackers now know how to stay hidden by blending in, and that makes it hard to tell when something’s wrong. This week’s stories aren’t just about what was attacked—but how...
Signal Blocks Windows Recall
This article gives a good rundown of the security risks of Windows Recall, and the repurposed copyright protection took that Signal used to block the AI feature from scraping Signal data...
Lattica Emerges from Stealth to Solve AI’s Biggest Privacy Challenge with FHE
Lattica’s cloud-based solution uses Fully Homomorphic Encryption to query encrypted data on AI models without decrypting it, preserving privacy and bolstering security...
AI Data Poisoning
Cloudflare has a new feature--available to free users as well--that uses AI to generate random pages to feed to AI web crawlers: Instead of simply blocking bots, Cloudflare's new system lures them into a "maze" of realistic-looking but irrelevant pages, wasting the crawler's computing resources...
A week in security (December 2 – December 8)
Last week on Malwarebytes Labs: Europol takes down criminal data hub Manson Market in busy month for law enforcement Americans urged to use encrypted messaging after large, ongoing cyberattack Crypto’s rising value likely to bring new wave of scams AI chatbot provider exposes 346,000 customer...
A week in security (July 8 – July 14)
Last week on Malwarebytes Labs: "Nearly all" AT&T customers had phone records stolen in new data breach disclosure Fake Microsoft Teams for Mac delivers Atomic Stealer Dangerous monitoring tool mSpy suffers data breach, exposes customer details iPhone users in 98 countries warned about spyware by...